cover
Contact Name
Eman Sulaiman
Contact Email
emans.aero@gmail.com
Phone
+6285222147610
Journal Mail Official
admin@ptbegin.com
Editorial Address
Jl. Pekalipan Selatan No 16. Cirebon
Location
Kab. banyumas,
Jawa tengah
INDONESIA
Journal of Computation Science And Artificial Intelligence
ISSN : -     EISSN : 30324653     DOI : https://doi.org/10.58468/
The Journal of Computation Science and Artificial Intelligence (JCSAI) is a double-blind peer-reviewed journal devoted to publishing original scientific articles on research and development in all fields of Computer Applications. Computational Science is a rapidly growing multi- and interdisciplinary field. It develops mathematical and computational models and uses advanced computing techniques to simulate these models, driven by data. Its overarching goal is to understand and solve complex problems. It has reached a level of predictive and interventional capability that now firmly complements the traditional pillars of experimentation and theory. The recent advances in experimental techniques have opened up new windows into physical and biological processes at many levels of detail. The resulting data explosion allows for detailed data-driven modeling and simulation which is no longer feasible using traditional analytical approaches alone. This new discipline in science combines computational thinking, modern computational methods, devices and collateral technologies to address problems far beyond the scope of traditional numerical methods. Journal of Computation Science and Artificial Intelligence (JCSAI) is a fully open access, international journal that aims to provide academia and industry with a venue for rapid publication of research manuscripts reporting innovative computational methods and applications to achieve a major breakthrough, practical improvements, and bold new research directions within a wide range of Computer applications. The objective of this journal is to communicate recent and projected advances in computer-based engineering techniques, with an emphasis on research and development leading to practical problem-solving. It will reflect the significant advances that are currently being made in computer science. The multidisciplinary character of this field will be typified by providing the readers with a broad range of articles. The Journal also provide an active forum for the dissemination of results in both research and advanced practice in computational engineering, to promote rapid communication and exchange between computer scientists, computational engineers and software developers. The journal especially encourages papers from new emerging and multidisciplinary areas, as well as papers reflecting the international trends of research and development aimed at a general computer science audience seeking a full and expert overview of the latest developments across computer science research. The journal is to keep related researchers updated on the developments in a wide range of topics reporting experiments, techniques and ideas that advance the understanding of various areas of computer science. Papers are solicited from, but not limited to the following topics: Ad-hoc, Mobile, Wireless Networks Approaches for Cloud/Fog/Edge computing Artificial Intelligence Automation and Mobile Robots Biometrics Communication Protocol Computational Intelligence Computer Application and Information Technology Computer Graphics and Computer Aided design Computer Networks and Communications Computer Vision and Pattern Recognition Cryptography and Computer Security Data Science & Machine Learning Data Warehouse & Data Mining Database Management Systems Design & Analysis of Algorithms Distributed computing Engineering software development Evolutionary Computing Expert and Decision Support Systems Fuzzy Computing Fuzzy Logic and Approximate Reasoning Genetic Algorithms and Modelling Hardware and architecture High-Performance Computing Human-Computer Interaction Human-Machine Interface IDS/Firewall, Anti-Virus Issues Image Processing and Computer Vision Systems Information and Communication Technology Information security Information Systems Intelligent Systems Internet of Things (IOT) Language and Search Engine Design Mobile Computing Multimedia and graphics Network Evolution Network Optimization Neuro Computing Parallel & distributed computing Quantum and Cloud Computing Signal/Image Processing Soft Computing Security Software Engineering education Software Engineering for AI systems Stochastic Models & Reinforcement Learning Systems Integration Virtual Reality Virtualized systems Vision/Pattern Recognition Visualization techniques Wireless Sensor Networks Computational science typically unifies three distinct elements: Modeling, Algorithms and Simulations (e.g. numerical and non-numerical, discrete and continuous); Software developed to solve science (e.g., biological, physical, and social), engineering, medicine, and humanities problems; Computer and information science that develops and optimizes the advanced system hardware, software, networking, and data management components (e.g. problem solving environments). The topics are included but are not necessarily restricted to:- Full-length original research papers of significant contributions Comprehensive and in-depth reviews on emerging techniques and methodologies Short communications on novel perspectives and breaking advancements in Computer applications. Tutorial survey type papers reviewing some fields of Computer Science and Engineering. Technical notes on projects, codes and standards are also welcomed.
Articles 28 Documents
metode vlsekriterijumsko kompromisno rangiranje (vikor) untuk menentukan lokasi gudang pada sinar alam caakrabuana Gina Putri Yustina; Kosim; Fajriatus Sholehah
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 2 No. 2 (2025): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v2i2.23

Abstract

Pemilihan lokasi gudang di PT. Sinar Alam Cakrabuana secara tradisional dilakukan secara manual, sehingga menimbulkan inefisiensi dan kesalahan perhitungan akibat banyaknya data yang diproses. Penelitian ini mengusulkan sistem pendukung keputusan menggunakan metode VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje) untuk menentukan lokasi gudang yang optimal di antara beberapa alternatif. VIKOR merupakan teknik pengambilan keputusan multikriteria (MCDM) yang menyeimbangkan kriteria yang saling bertentangan dan tidak sepadan dengan menggabungkan faktor objektif dan subjektif. Kriteria yang dipertimbangkan meliputi jarak tempuh, waktu tempuh, kondisi jalan, dan keamanan, yang masing-masing diberi bobot tertentu. Hasil penelitian menunjukkan bahwa metode VIKOR efektif dalam memeringkat alternatif dan mengidentifikasi lokasi terbaik. Sistem ini mengurangi kesalahan manusia, meningkatkan akurasi keputusan, dan mempercepat proses pemilihan. Penelitian ini menunjukkan penerapan VIKOR dalam perencanaan lokasi gudang dalam konteks industri nyata. Abstract The selection of warehouse locations at PT. Sinar Alam Cakrabuana has traditionally been conducted manually, leading to inefficiencies and calculation errors due to the volume of data processed. This study proposes a decision support system using the VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje) method to determine the optimal warehouse location among several alternatives. VIKOR is a multi-criteria decision-making (MCDM) technique that balances conflicting and non-commensurable criteria by combining objective and subjective factors. The criteria considered include travel distance, travel time, road conditions, and security, each assigned specific weights. The results show that the VIKOR method effectively ranks alternatives and identifies the best location. The system reduces human error, improves decision accuracy, and accelerates the selection process. This research demonstrates the applicability of VIKOR in warehouse location planning within a real industrial context.
VISUAL SEMIOTIC ANALYSIS OF GAMIFICATION ELEMENTS IN DUOLINGO GERMAN Azah Afifah; Odi Nurdiawan; Arif Rinaldi Dikananda
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 3 No. 1 (2026): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v3i1.24

Abstract

The advancement of digital technology has accelerated the growth of Mobile Assisted Language Learning (MALL), with Duolingo as one of the most popular gamified language-learning applications. This study analyzes the visual semiotics of gamification elements in the Duolingo German interface (versions 2022–2025). A descriptive qualitative approach with a case study design is employed. Data consist of screenshots of gamification elements (XP, streak, badges, leaderboard, mascot, and feedback animations) and related literature, analyzed using Roland Barthes’ semiotics, the Shannon and Weaver communication model, and Self Determination Theory within a sociocultural framework. The findings show that visual gamification elements construct the myth of an ideal learner who is always productive, consistent, and competitive. These elements have a dual motivational effect: they can both strengthen and undermine the needs for competence, autonomy, and relatedness, depending on users’ cultural context and meaning-making. The study enriches visual semiotics and gamified language learning research and offers UI/UX recommendations for developers and educators to design more humanistic and meaningful learning experiences. Abstrak Kemajuan teknologi digital telah mempercepat pertumbuhan Pembelajaran Bahasa Berbantuan Seluler (Mobile Assisted Language Learning/MALL), dengan Duolingo sebagai salah satu aplikasi pembelajaran bahasa berbasis gamifikasi yang paling populer. Studi ini menganalisis semiotika visual elemen gamifikasi dalam antarmuka Duolingo Jerman (versi 2022–2025). Pendekatan kualitatif deskriptif dengan desain studi kasus digunakan. Data terdiri dari tangkapan layar elemen gamifikasi (XP, streak, lencana, papan peringkat, maskot, dan animasi umpan balik) dan literatur terkait, yang dianalisis menggunakan semiotika Roland Barthes, model komunikasi Shannon dan Weaver, dan Teori Penentuan Diri dalam kerangka sosiokultural. Temuan menunjukkan bahwa elemen gamifikasi visual membangun mitos tentang pembelajar ideal yang selalu produktif, konsisten, dan kompetitif. Elemen-elemen ini memiliki efek motivasi ganda: mereka dapat memperkuat dan melemahkan kebutuhan akan kompetensi, otonomi, dan keterkaitan, tergantung pada konteks budaya dan pemahaman makna pengguna. Studi ini memperkaya semiotika visual dan penelitian pembelajaran bahasa yang digamifikasi, serta menawarkan rekomendasi UI/UX bagi pengembang dan pendidik untuk merancang pengalaman belajar yang lebih humanistik dan bermakna.
METODE ARAS (ADDITIVE RATIO ASSESSMENT) PENENTUAN PENERIMA BANTUAN PUPUK DI DINAS KETAHANANPANGAN PERTANIAN DAN PERIKANAN MAJALENGKA Susi Widyastuti; Asep Kosasih; Afrizal Malik Fajar
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 3 No. 1 (2026): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v3i1.25

Abstract

Kabupaten Majalengka di Jawa Barat memiliki potensi pertanian yang kaya, dengan fokus utama pada komoditas seperti padi, jagung, dan kedelai. Namun, penyaluran bantuan pupuk oleh Dinas Ketahanan Pangan, Pertanian, dan Perikanan Majalengka kepada kelompok tani menghadapi tantangan dalam menentukan penerima yang berhak. Masalah ini disebabkan oleh kurangnya data yang terkumpul dan proses analisis manual yang memakan waktu. Penelitian ini menghadirkan solusi dengan menerapkan Sistem Pendukung Keputusan (SPK) menggunakan Metode Additive Ratio Assessment (ARAS), yang didasarkan pada prinsip intuitif bahwa alternatif harus memiliki rasio terbesar untuk menghasilkan solusi yang optimal. Hasil dari penelitian ini menunjukkan bahwa penerapan ARAS berhasil memberikan peringkat yang akurat, dengan kelompok tani "LEUWEUNG SALAM" mendapatkan peringkat tertinggi, yaitu 0.7270. Dengan demikian, implementasi ARAS dapat membantu Dinas Ketahanan Pangan, Pertanian, dan Perikanan Majalengka dalam meningkatkan efisiensi penyaluran bantuan pupuk ke kelompok tani yang memenuhi kriteria yang telah ditetapkan. Abstract Majalengka Regency in West Java boasts a rich agricultural potential, with a primary focus on commodities such as rice, corn, and soybeans. However, the distribution of fertilizer assistance by the Majalengka Regency Department of Food Security, Agriculture, and Fisheries to farmer groups faces challenges in determining eligible recipients. This issue is primarily attributed to the lack of collected data and the time-consuming manual analysis process. This study offers a solution by implementing a Decision Support System (DSS) using the Additive Ratio Assessment (ARAS) method, which is based on the intuitive principle that alternatives must have the highest ratio to yield an optimal solution. The results of this research demonstrate that the application of ARAS successfully provides accurate rankings, with the "LEUWEUNG SALAM" farmer group receiving the highest rank of 0.7270. Thus, the implementation of ARAS can assist the Majalengka Regency Department of Food Security, Agriculture, and Fisheries in enhancing the efficiency of fertilizer distribution to farmer groups that meet the established criteria.
PENERAPAN ALGORITMA KRIPTOGRAFI ELGAMAL DAN SHA-256 PADA APLIKASI PENGOLAHAN DATA ATP-WTP UNTUKPENGAMANAN DATA RESPONDEN Muhammad Erwanto; Fajriatus Sholihah; Sugeng Wahyudi
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 3 No. 1 (2026): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v3i1.26

Abstract

According to Law Number 16 of 1997 concerning of Statistics, Article 21 states that the organizers of statistical activities are obliged to protect the confidentiality of individual data from respondents. BPS Cirebon Regency as the organizer of statistical activities is obliged to protect individual respondent data. Cryptography provides services to secure data by transforming it so that the data can no longer be read. The cryptographic algorithm used in this study is the ElGamal Algorithm, this algorithm was chosen because of its reliability in maintaining plaintext. However, this does not rule out the possibility of inserting messages into the ciphertext so that it will damage the message when deciphering is done, but this can be overcome using checksums. SHA256 as a standard algorithm created by NIST is used to maintain the integrity of ciphertext files. The data used in this study is in the form of data from the processing of the ATP-WTP survey (ability to pay and willingness to pay) organized by the Central Bureau of Statistics of Cirebon Regency. Abstrak Berdasarkan UU Nomor 16 Tahun 1997 Tentang Statistik, pada pasal 21 disebutkan bahwa penyelenggara kegiatan statistik wajib melindungi kerahasiaan data individu dari responden. BPS Kabupaten Cirebon sebagai penyelenggara kegiatan statistik wajib melindungi data individu responden. Kriptografi menyediakan layanan untuk mengamankan data dengan cara melakukan transformasi sehingga data tersebut tidak lagi dapat dibaca. Algoritma kriptografi yang digunakan dalam penelitian ini adalah Algoritma ElGamal, algoritma ini dipilih karena kehandalannya dalam menjaga plainteks. Namun hal tersebut tidak menutup kemungkinan terjadinya penyisipan pesan ke dalam ciphertext sehingga akan membuat rusak pesan pada saat dilakukan deciphering, namun hal tersebut dapat diatasi menggunakan checksum. SHA256 sebagai algoritma standar yang dibuat oleh NIST di gunakan untuk menjaga integritas file ciphertext. Adapun Data yang digunakan dalam penelitian ini adalah berupa data hasil pengolahan survei ATP-WTP (ability to pay and willingness to pay) yang diselenggarakan oleh Badan Pusat Statistik Kabupaten Cirebon.    
METODE ALGORITMA RC4 (RIVEST CODE 4) UNTUK PENGAMANAN DATABASE TRANSAKSIPADA GLORY DIGITAL SABLON Wahyu Ariandi; Faisal Akbar; M. Rezza Fahlevi; Adiguna Ahlul Bai’at
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 3 No. 1 (2026): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v3i1.27

Abstract

Kemajuan teknologi informasi dan komunikasi memfasilitasi penyelesaian pekerjaan dengan lebih cepat, mudah, dan akurat. Glory Digital Sablon (GDS) adalah toko yang menyediakan berbagai kebutuhan terkait sablon digital, namun sistem penjualannya masih manual, sementara pembuatan nota menggunakan Microsoft Excel yang memiliki kekurangan dan kendala. Penelitian ini bertujuan untuk merancang sistem yang otomatis, serta memperkenalkan algoritma kriptografi RC4 untuk mengamankan database transaksi dan database supplier agar tidak disalahgunakan. Penerapan algoritma RC4 terbukti efektif dalam mengamankan data transaksi pada GDS, dengan kunci enkripsi yang dapat diacak berdasarkan panjang kunci, dan dapat mengembalikan data asli melalui dekripsi dengan kunci yang sama. Pengujian CrackStation menunjukkan bahwa cipherteks tidak dapat dipecahkan, dan uji performa menunjukkan bahwa meskipun panjang kunci memengaruhi kecepatan enkripsi dan dekripsi, perbedaannya sangat kecil, sehingga tidak mempengaruhi kinerja keseluruhan sistem. Abstract Advances in information and communication technology facilitate faster, easier, and more accurate work completion. Glory Digital Sablon (GDS) is a store that provides various needs related to digital screen printing, but its sales system is still manual, while the creation of invoices uses Microsoft Excel which has shortcomings and obstacles. This study aims to design an automated system, as well as introduce the RC4 cryptographic algorithm to secure the transaction database and supplier database from misuse. The implementation of the RC4 algorithm has proven effective in securing transaction data on GDS, with encryption keys that can be randomized based on key length, and can restore the original data through decryption with the same key. CrackStation testing shows that the ciphertext cannot be cracked, and performance tests show that although key length affects encryption and decryption speed, the difference is very small, so it does not affect the overall performance of the system.
ALGORITMA K-MEANS UNTUK CLUSTERING DATA PENYITAAN BARANG BUKTI KEJAHATAN PADA POLRES CIREBON Virgiyanti; Kosim; Rizky Insan Khamil
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 3 No. 1 (2026): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v3i1.28

Abstract

Evidence is a crucial element in the criminal justice system used to prove the occurrence of a crime. The manual management of evidence by investigators often leads to errors in recording and difficulties in tracking the evidence. This study aims to develop a web-based application that uses the K-Means algorithm to cluster confiscated evidence data at the Cirebon Police Department. The results show that the K-Means algorithm effectively grouped the evidence into three categories based on the severity of the crime: minor, moderate, and serious crimes. The system proved to be effective in improving the efficiency of evidence management, reducing errors in manual recording, and facilitating the analysis of crime severity based on the confiscated evidence. Abstrak Barang bukti merupakan elemen penting dalam sistem peradilan pidana yang digunakan untuk membuktikan peristiwa tindak pidana. Pengelolaan barang bukti yang dilakukan secara manual oleh penyidik sering kali menyebabkan kesalahan pencatatan dan kesulitan dalam pelacakan barang bukti. Penelitian ini bertujuan untuk mengembangkan aplikasi berbasis web yang menggunakan algoritma K-Means untuk mengelompokkan data penyitaan barang bukti di Polres Cirebon. Hasil penelitian menunjukkan bahwa algoritma K-Means berhasil mengelompokkan barang bukti ke dalam tiga kategori berdasarkan tingkat kejahatan: ringan, sedang, dan berat. Sistem ini terbukti efektif dalam meningkatkan efisiensi pengelolaan data barang bukti, mengurangi kesalahan pencatatan manual, dan mempermudah analisis tingkat kejahatan berdasarkan barang bukti yang ditemukan.
A Safety-Aware Retrospective Audit of a Certainty-Factor Expert System for Formalin-Risk Screening Muhammad Erwanto; Rd. Radian Baratasena; Adiksi Firmansyah
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 3 No. 2 (2026): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v3i2.30

Abstract

Observable characteristics can support early food-safety triage, but they cannot chemically confirm formaldehyde. This study presents a safety-aware retrospective technical audit and algorithmic reconstruction of a legacy web-based certainty-factor (CF) expert system previously used as a prototype for food screening. The available evidence comprised interface artifacts, a food-category summary, legacy rule values, and one manually reconstructable fish scenario; source code, laboratory measurements, and a detailed fish calculation trace were unavailable. Expert and user CF values were multiplied for each positive evidence item and aggregated iteratively. The fish contributions of 0.42, 0.40, 0.12, and 0.28 produced an exact reconstructed score of 0.7795072, consistent only with the prototype summary value of 78%; a detailed interface-level trace for fish could not be verified. A deterministic verification suite confirmed expected behavior for empty, zero, unit, single-evidence, order-invariance, and invalid-input cases in the reconstructed reference algorithm. The audit also identified unsafe legacy remediation text and insufficient rule provenance. The revised architecture therefore separates screening from laboratory confirmation and introduces versioned rules, input snapshots, calculation lineage, and referral records. The contribution is a transparent audit framework for legacy rule-based screening systems. The CF score remains a rule-consistency measure and must not be interpreted as formalin concentration, contamination probability, predictive accuracy, or a substitute for validated chemical testing. ABSTRAK Karakteristik yang dapat diamati dapat mendukung triase awal keamanan pangan, tetapi tidak dapat mengonfirmasi formaldehida secara kimia. Penelitian ini menyajikan audit teknis retrospektif yang berorientasi keselamatan serta rekonstruksi algoritmik terhadap prototipe lama sistem pakar berbasis web dengan metode Certainty Factor (CF). Bukti yang tersedia terdiri atas artefak antarmuka, ringkasan kategori pangan, nilai aturan lama, dan satu skenario ikan yang dapat direkonstruksi secara manual; kode sumber, pengukuran laboratorium, dan jejak perhitungan terperinci untuk ikan tidak tersedia. Nilai CF pakar dan pengguna dikalikan untuk setiap bukti positif, kemudian diagregasikan secara iteratif. Kontribusi skenario ikan sebesar 0,42; 0,40; 0,12; dan 0,28 menghasilkan skor rekonstruksi tepat 0,7795072, yang hanya konsisten dengan nilai ringkasan prototipe sebesar 78%; jejak perhitungan ikan pada tingkat antarmuka tidak dapat diverifikasi. Serangkaian uji deterministik mengonfirmasi perilaku algoritma rekonstruksi untuk kasus kosong, nol, satu, bukti tunggal, perubahan urutan, dan input tidak valid. Audit juga menemukan teks mitigasi lama yang tidak aman dan asal-usul bobot aturan yang tidak memadai. Arsitektur revisi memisahkan skrining dari konfirmasi laboratorium serta menambahkan versi aturan, snapshot input, jejak perhitungan, dan catatan rujukan. Skor CF tetap merupakan ukuran konsistensi terhadap aturan dan bukan kadar formalin, probabilitas kontaminasi, akurasi prediktif, atau pengganti pengujian kimia tervalidasi.
Evaluasi prototipe absensi mahasiswa berbasis Eigenface pada skenario kelas multiwajah Susi Widyastuti; Faisal Akbar; Rifqi Arnoldy Rachman
Journal of Computation Science and Artificial Intelligence (JCSAI) Vol. 3 No. 2 (2026): Journal of Computation Science and Artificial Intelligence (JCSAI)
Publisher : PT. Berkah Digital Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58468/jcsai.v3i2.31

Abstract

Automated attendance systems based on facial biometrics can reduce manual recording, but their deployment requires a clear separation between face detection and identity recognition. This study evaluates an Eigenface-based attendance prototype in a multi-face classroom setting and reanalyzes the archived test results using a reproducible statistical protocol. The prototype processes camera frames through face localization, grayscale conversion, cropping and resizing, principal component analysis projection, Euclidean-distance matching, and attendance recording. The available evaluation comprised 30 trials, each containing 17 target faces, yielding 510 face-detection opportunities. Trial-level detection coverage was defined as the number of detected faces divided by 17. Across all trials, 310 faces were detected, corresponding to an aggregate coverage of 60.78%. Trial-level coverage ranged from 29.41% to 82.35%, with a mean of 60.78%, a standard deviation of 14.44 percentage points, and a 95% t-confidence interval of 55.39%–66.17%. These results demonstrate that the prototype can execute the intended attendance workflow but is not yet sufficiently reliable for unsupervised operational use. Because the archived data contain only detected-face counts, they cannot establish identity-recognition accuracy, false acceptance, or false rejection. The study contributes a corrected evaluation of the prototype, an explicit distinction between detection and recognition evidence, and a deployment-readiness framework for subsequent controlled validation.   ABSTRAK Sistem absensi otomatis berbasis biometrik wajah berpotensi mengurangi pencatatan manual, tetapi penerapannya memerlukan pemisahan yang jelas antara deteksi wajah dan pengenalan identitas. Penelitian ini mengevaluasi prototipe absensi berbasis Eigenface pada skenario kelas multiwajah dan menganalisis ulang hasil pengujian arsip menggunakan protokol statistik yang dapat ditelusuri. Prototipe memproses bingkai kamera melalui lokalisasi wajah, konversi ke skala abu-abu, pemotongan dan perubahan ukuran citra, proyeksi principal component analysis, pencocokan menggunakan Euclidean distance, serta pencatatan kehadiran. Evaluasi yang tersedia terdiri atas 30 percobaan dengan 17 wajah target pada setiap percobaan sehingga menghasilkan 510 peluang deteksi. Cakupan deteksi setiap percobaan dihitung sebagai jumlah wajah terdeteksi dibagi 17. Secara keseluruhan, 310 wajah terdeteksi atau setara dengan cakupan agregat 60,78%. Cakupan per percobaan berkisar antara 29,41% dan 82,35%, dengan rata-rata 60,78%, simpangan baku 14,44 poin persentase, dan interval kepercayaan t 95% sebesar 55,39%–66,17%. Hasil tersebut menunjukkan bahwa prototipe dapat menjalankan alur absensi, tetapi belum cukup andal untuk digunakan tanpa pengawasan. Karena data arsip hanya memuat jumlah wajah terdeteksi, hasil ini belum dapat membuktikan akurasi identifikasi, penerimaan salah, maupun penolakan salah. Kontribusi penelitian adalah koreksi evaluasi prototipe, pemisahan bukti deteksi dan pengenalan, serta kerangka kesiapan penerapan untuk validasi lanjutan.

Page 3 of 3 | Total Record : 28